PASSION Project: Data Collection in Madagascar and Guinea
Bibliographic record
Abstract
Background Little data on dermatological conditions presenting on African skin are currently available. This is partly due to the lack of dermatologists in African countries, such as Madagascar and Guinea. There are only 13 dermatologists in Madagascar, or one dermatologist for every 2 million inhabitants. By contrast, the prevalence of common dermatosis is constantly increasing, especially among the pediatric population. According to the World Health Organization, 80% of these skin problems in Africa are grouped into the following 5 pathologies: atopic dermatitis, dermatophytosis, scabies, impetigo, and insect bites. Objective In the face of this dilemma, artificial intelligence (AI) is a better tool to collect data on a national scale. Madagascar began participating in the PASSION project in June 2020 and Guinea began participating in January 2021. They join other countries, like Switzerland, Australia, China, India, and Tanzania, who are also using AI in dermatology. This study mainly aimed to compare the 5 pathologies according to the different phototypes characterizing these countries and to collect cases on a national scale that will form a national database. The aim of the data collection is to add 1000 cases per year to the database. Methods To increase the number of cases included in phototypes III to VI, two countries were included. A total of 6 data collection sites were set up in Madagascar and one was set up in Guinea. Patients were recruited during dermatology consultations. All patients presenting the 5 pathologies were included. A total of 3 platforms were used to collect data: my.crf.one, IntelliStream, and Derma2go. Results A total of 323 cases are currently included in the database for Madagascar, including 76 cases of scabies, 111 cases of atopic dermatitis, 94 cases of dermatophytosis, 35 cases of impetigo and 11 cases of insect bites. The patients’ ages ranged from 2 months to 68 years. A male predominance was noted, with a sex ratio of 1.19 (109 males and 91 females). Phototypes ranged from III to VI. For Guinea, 178 total cases included 32 cases of scabies, 26 cases of atopic dermatitis, 92 cases of dermatophytosis, 3 cases of impetigo, and 25 cases of insect bites. Patients’ ages ranged between 1 year and 70 years, with a male predominance, a sex ratio of 1.54 (108 males and 70 females), and a predominance of phototype VI. Conclusions AI is a data collection solution in Africa. However, high bandwidth is needed to employ AI. Conflicts of Interest None declared.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.011 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".